Forging Multiple Training Objectives for Pre-trained Language Models via Meta-LearningDownload PDF


17 Apr 2022 (modified: 05 May 2023)ACL ARR 2022 April Blind SubmissionReaders: Everyone
Abstract: Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios. However, learning multiple training objectives in a single model is challenging due to the unknown relative significance as well as the potential contrariety between them. Empirical studies have shown that the current objective sampling in an ad-hoc manual setting makes the learned language representation barely converge to the desired optimum. Thus, we propose $MOMETAS$, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives. The design is lightweight with little additional training overhead. To validate our approach, we adopt five objectives and conduct continual pre-training with BERT-base, BERT-large models, where MOMETAS demonstrates universal performance gain over other rule-based sampling strategies on 14 natural language processing tasks.
Paper Type: long
0 Replies